INDEX
    Explanations

    references to articles of clothing, specifically hoods

    references to hoods in various contexts, including clothing and vehicle parts

    New Auto-Interp
    Negative Logits
    MENT
    -0.80
    tery
    -0.73
    lihood
    -0.71
     Lauder
    -0.71
    andum
    -0.70
    MENTS
    -0.69
    FORM
    -0.68
    ngth
    -0.68
    ×ķ
    -0.68
     VIDEOS
    -0.68
    POSITIVE LOGITS
    oos
    1.12
    sie
    1.11
     ornament
    1.09
    ie
    1.07
    oo
    0.99
    ies
    0.96
    elled
    0.94
    tip
    0.93
    ed
    0.92
    iery
    0.91
    Act Density 0.068%

    No Known Activations